Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty and lack of clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     us
    -0.35
     itself
    -0.31
     me
    -0.30
    ç»ĻæĪij
    -0.29
     themselves
    -0.29
    让æĪij
    -0.27
     мне
    -0.25
     mij
    -0.23
    us
    -0.23
     Us
    -0.21
    POSITIVE LOGITS
     ourselves
    0.99
     our
    0.61
    æĪij们çļĦ
    0.47
    our
    0.47
    ours
    0.46
     наÑĪиÑħ
    0.46
     noss
    0.45
     nuestros
    0.42
    Our
    0.42
     nosso
    0.42
    Act Density 1.147%

    No Known Activations